© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 108450
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to electrical connections and mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noh
    -0.06
     target
    -0.06
     Swap
    -0.06
     vigil
    -0.06
    ((((
    -0.06
     synthetic
    -0.06
     вдÑĢÑĥг
    -0.06
     exit
    -0.06
     Exit
    -0.06
     savoir
    -0.06
    POSITIVE LOGITS
    pler
    0.08
    øy
    0.08
    GENCY
    0.08
    ån
    0.07
    -machine
    0.07
    INGLE
    0.07
     Cycl
    0.07
    ount
    0.07
     MACHINE
    0.07
    ãĥ³ãĥIJãĥ¼
    0.07
    Activations Density 0.001%

    No Known Activations